当前位置: 首页 >> 师资队伍 >> 副教授 >> 正文
严严 副教授

清华大学 博士(2009)

研究方向:计算机视觉 模式识别 图像处理

所属部门:计算机科学系

电子邮件:yanyan (AT) xmu.edu.cn

个人主页:http://information.xmu.edu.cn/portal/node/72

个人简历:

主讲课程: 

数字信号处理(专业必修)(本科生课程)

计算机科学与技术导论(专业必修)(本科生课程)

Matlab程序设计(全校选修)(本科生课程)

C语言程序设计(公共基础课)(本科生课程)

计算机基础(公共基础课)(本科生课程)

指导研究生: 

2011级 研究生:晏栋(现腾讯工作)

2012级 研究生:沈媛媛(现中科院自动化所读博)

2013级 研究生:陈日伟(现今日头条工作);刘敏(现公安部交科所工作)

2014级 研究生:方媛(现阿里巴巴工作);谢超超(现招银网络科技工作)

2015级 研究生:庄妮(现奇虎360工作);苏灿平(现美图科技工作)

2016级 研究生:杨婉香(现网速科技工作);黄颖(现准动网络科技工作)

2017级 研究生:董根顺;毛龙彪;孟祥邦

学术兼职: 

IEEE会员
中国计算机学会计算机视觉专委会委员
中国图像图形学学会会员
ACM ICIMCS 2014本地主席
IEEE FMT 2018本地主席
IEEE Transactions on Image Processing, IEEE Transaction on Neural Network and Learning Systems, IEEE Transactions on Circuits and Systems for Video Technology, Pattern Recognition, Journal of Visual Communication and Image Representation, Neurocomputing, 计算机学报, 计算机研究与发展, 电子与信息学报等期刊审稿人


获奖情况:


《厦门大学学报(自然科学版)》优秀论文奖, 2018
VCIP 国际会议最佳10%论文奖(Best 10% Paper), 2016
厦门大学第十届青年教师教学技能比赛 二等奖, 2015
NOKIA PHOTO BROWSER, OVI在线推荐下载软件奖 (MUST-HAVE application award), 2010

在研项目: 

国家自然科学基金面上项目(项目负责人)—基于深度学习的人脸识别关键技术研究, 2016.01-2019.12
国家重点研发计划“智能机器人”重点专项项目(子项目负责人)—服务机器人云服务平台, 2018.01-2020.12
福建省自然科学基金面上项目(项目负责人)—基于视觉传感器与光纤陀螺融合的人脸跟踪识别算法研究, 2017.04-2020.04
厦门大学校长基金(项目负责人)—基于视觉SLAM和LED的室内定位技术研究, 2017.01-2019.12
国家自然科学基金青年项目(项目负责人)—基于距离度量学习和类依赖特征分析的人脸特征提取方法研究, 2013-2015
福建省自然科学基金项目(项目负责人)—基于半正定度量学习的大规模人脸聚类算法研究, 2012-2014
PANASONIC新加坡研究院多媒体处理组(项目负责人)—图像识别系统开发, 2011
NOKIA日本研发中心图像软件组(项目核心成员)—嵌入式平台人脸识别系统开发, 2009-2010
清华大学电子工程系图像工程实验室(项目核心成员)—人脸识别中的鉴别特征提取技术研究, 2004-2009

代表性论文: 

•期刊论文:
Longbiao Mao, Yan Yan*, Jing-Hao Xue, Hanzi Wang. Deep multi-task multi-label CNN for effective facial attribute classification. IEEE Transactions on Affective Computing, 2020. (JCR 2区)
Genshun Dong, Yan Yan*, Chunhua Shen, Hanzi Wang. Real-time high-performance semantic image segmentation of urban street scenes. IEEE Transactions on Intelligent Transportation Systems, 2020. (JCR 2区)
Yan Yan, Zizhao Zhang, Si Chen, Hanzi Wang, Low-resolution Facial Expression Recognition: A Filter Learning Perspective. Signal Processing, 169 (107370):1-13, 2020. (JCR 2区)
Yan Yan*, Ying Huang, Si Chen, Chunhua Shen, Hanzi Wang. Joint deep learning of facial expression synthesis and recognition. IEEE Transactions on Multimedia, 2020. (JCR 2区)
Guanjun Guo, Hanzi Wang, Yan Yan, Liming Zhang, Bo Li, Large Margin deep embedding for aesthetic image classification. SCIENCE CHINA Information Sciences, 2020, 63(1): 119102.
Guobao Xiao, Xiong Zhou, Yan Yan, Hanzi Wang. A two-step hypergraph reduction based fitting method for unbalanced data. Pattern Recognition Letters, 2020. (JCR 3区)
Taotao Lai, Hanzi Wang, Yan Yan, Tat-Jun Chin, Jin Zheng, Bo Li. Accelerated guided sampling for multi-structure model fitting. IEEE Transactions on Cybernetics, 2020. (JCR 1区)
Guanjun Guo, Hanzi Wang, Yan Yan, Jin Zheng, Bo Li, A fast face detection method via convolutional neural network, Neurocomputing, 2020. (JCR 2区)
Yihan Du, Yan Yan*, Si Chen, Yang Hua. Object-adaptive LSTM network for real-time visual tracking with adversarial data augmentation. Neurocomputing, 2020. (JCR 2区)
Hanzi Wang, Guobao Xiao, Yan Yan, David Suter. Searching for representative modes on hypergraphs for robust geometric model fitting. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 41(3):697-711, 2019. (JCR 1区)
Guobao Xiao, Hanzi Wang, Yan Yan, David Suter, Superpixel-Guided Two-View Deterministic Geometric Model Fitting. International Journal of Computer Vision (IJCV), 127(4):323-339, 2019. (JCR 1区)
Wanxiang Yang, Yan Yan, Si Chen. Adaptive Deep Metric Embeddings for Person Re-Identification under Occlusions. Neurocomputing, 336:56-66, 2019. (JCR 2区)
Liao Zhang, Yan Yan, Lin Cheng, Hanzi Wang. Learning Object Scale with Click Supervision for Object Detection. IEEE Signal Processing Letters, 26(11):1618-1622, 2019. (JCR 3区)
Guanjun Guo, Hanzi Wang, Wan-Lei Zhao, Yan Yan, Xuelong Li. Object discovery via cohesion measurement. IEEE Transactions on Cybernetics (T-CYB), 48(3): 862-875, 2018. (JCR 1区)
Guanjun Guo, Hanzi Wang, Chunhua Shen, Yan Yan, Mark Liao. Automatic image cropping for visual aesthetic enhancement using deep neural networks and cascaded regression. IEEE Transactions on Multimedia (T-MM), 20(8):2073-2085, 2018. (JCR 2区)
Ni Zhuang, Yan Yan, Si Chen, Hanzi Wang, Chunhua Shen. Multi-label learning based deep transfer neural network for facial attribute classification. Pattern Recognition (PR), 80:225-240, 2018. (JCR 2区)
Zizhao Zhang, Fuyong Xing, Hanzi Wang, Yan Yan, Ying Huang, Xiaoshuang Shi, Lin Yang. Revisiting graph construction for fast image segmentation. Pattern Recognition (PR), 78: 344-357, 2018. (JCR 2区)
Yan Yan, Min Liu, Si Chen, and Fan Xiao. A novel robust model fitting approach towards multiple-structure data segmentation. Neurocomputing, 239: 181-193, 2017. (JCR 2区)
Taotao Lai, Hanzi Wang, Yan Yan, Tat-Jun Chin, Wanlei Zhao. Motion segmentation via a sparsity constraint. IEEE Trans. Intelligent Transportation Systems, 18(4): 973-983, 2017. (JCR 2区)
Li Qiming, Hanzi Wang, Yan Yan, Bo Li, Changwen Chen. Local co-occurrence selection via partial least squares for pedestrian detection. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(6): 1549-1558. (JCR 2区)
Taotao Lai, Hanzi Wang, Yan Yan, Guobao Xiao, and David Suter. Efficient guided hypothesis generation for multi-structure epipolar geometry estimation. Computer Vision and Image Understanding, 154: 152-165, 2017. (JCR 3区)
Taotao Lai, Hanzi Wang, Yan Yan, Liming Zhang. A unified hypothesis generation framework for multi-structure model fitting. Neurocomputing, 222: 144-154, 2017. (JCR 2区)
Yan Yan, Hanzi Wang, Si Chen, Xiaochun Cao, David Zhang. Quadratic projection based feature extraction with its application to biometric recognition. Pattern Recognition 56:40-49, 2016. (JCR二区)
Qiming Li, Yan Yan, Hanzi Wang. Discriminative weighted sparse partial least squares for human detection. IEEE Transactions on Intelligent Transportation Systems, 17(4):1062-1071, 2016. (JCR 2区)
Si Chen, Shaozi Li, Rongrong Ji, Yan Yan, Shunzhi Zhu. Discriminative local collaborative representation for online object tracking. Knowlege-Based Systems, 100: 13-24, 2016. (JCR 2区)
Zhongwei Tan, Chuanchuan Yang, Yuliang Li, Yan Yan, Changhong He, Xinyue Wang, Ziyu Wang, A low-complexity sensor fusion algorithm based on a fiber-optic gyroscope aided camera pose estimation system. SCIENCE CHINA Information Sciences,DOI:10.1007/s11432-015-5516-2, 2016. (中国科学信息科学,SCI检索)
Jianyu Tang, Hanzi Wang, Yan Yan, Learning Hough regression models via bridge partial least squares for object detection, Neurocomputing, 152, pp. 236-249, 2015. (JCR 2区)
Jun Wang, Hanzi Wang, Yan Yan, Robust visual tracking by metric learning with weighted histogram representations, Neurocomputing, 153, pp. 77-88, 2015. (JCR 2区)
Yan Yan, Chunhua Shen, Hanzi Wang, Efficient semidefinite spectral clustering via Lagrange duality, IEEE Transactions on Image Processing (TIP), 2014, 23(8):3522-3534. (JCR 2区)
Yan Yan, Hanzi Wang, David Suter. Multi-subregion based correlation filter bank for robust face recognition, Pattern Recognition (PR), 2014, 47(11):3487-3501. (JCR 2区)
沈媛媛, 严严*, 王菡子. 有监督的距离度量学习算法研究进展. 自动化学报, 2014, 40(12): 2673-2686. (国内EI权威期刊)
Yan Yan, Hanzi Wang, Cuihua Li, Bineng Zhong. An effective unconstrained correlation filter and its kernelization for face recognition, Neurocomputing, 2013, 119: 201-211. (JCR 2区)
严严,章毓晋. 基于视频的人脸识别研究进展. 计算机学报,2009, 32(5):878-886. (国内EI权威期刊)
Yan Yan, Yujin Zhang, 1-D correlation filter based class-dependence feature analysis for face recognition, Pattern Recognition (PR), 2008, 41(12): 3834-3841. (JCR 2区)
Yan Yan, Yujin Zhang, Discriminant projection embedding for face and palmprint recognition, Neurocomputing, 2008, 71(16): 3534-3543. (JCR 2区)
Yan Yan, Yujin Zhang, Tensor correlation filter based class-dependence feature analysis for face recognition, Neurocomputing, 2008, 71(16): 3434-3438. (JCR 2区)
Yan Yan, Yujin Zhang, A novel class-dependence feature analysis for face recognition, Pattern Recognition Letters (PRL), 2008, 29(14): 907-1914. (JCR 3区)
•会议论文:
Shuyuan Lin, Guobao Xiao, Yan Yan, Hanzi Wang, David Suter. Hypergraph optimization for multi-structural geometric model fitting. Proceedings of AAAI Conference on Artificial Intelligence, 2019. (CCF A 类)
Luo Xiong, Yanjie Liang, Yan Yan, Hanzi Wang. Correlation filter tracking with adaptive proposal selection for accurate scale estimation. Proceedings of IEEE International Conference on Multimedia & Expo, 2019. (CCF B 类)
Xiangbang Meng, Yan Yan, Si Chen, Hanzi Wang. A cascaded noise-robust deep CNN for face recognition. Proceedings of International Conference on Image Processing, 2019. (CCF C 类)
Lijian Lin, Haosheng Chen, Yanjie Liang, Yan Yan, Hanzi Wang. Robust visual tracking via statistical positive sample generation and gradient aware learning. ACM MM Asia, 2019.
Yanjie Liang, Qiangqiang Wu, Yi Liu, Yan Yan, Hanzi Wang. Robust Correlation Filter Tracking with Shepherded Instance-Aware Proposals, ACM Multimedia (MM), 2018. (CCF A 类)
Ni Zhuang, Yan Yan, Si Chen, Hanzi Wang. Multi-task learning of cascaded CNN for facial attribute classification. Proceedings of the IEEE Conference on Pattern Recognition (ICPR), 2018. (CCF C 类)
Yihan Du, Yan Yan, Si Chen, Yang Hua, Hanzi Wang object-Adaptive LSTM network for visual tracking. Proceedings of the IEEE Conference on Pattern Recognition (ICPR), 2018. (CCF C 类)
Chunguang Qie, Guo Guanjun, Yan Yan, Zhang Liming, Hanzi Wang*. Improved correlation filter tracking with hard negative mining. Proceedings of the IEEE Conference on Pattern Recognition (ICPR), 2018. (CCF C 类)
Jian Liao, Hanzi Wang, Yan Yan, Jin Zheng. A Novel Background Subtraction Method Based on ViBe. Pacific-Rim Conference on Multimedia (PCM), 2017. (CCF C 类)
Chunguang Qie, Hanzi Wang, Yan Yan, Guanjun Guo, Jin Zheng. Adaptive Correlation Filter Tracking with Weighted Foreground Representation. Pacific-Rim Conference on Multimedia (PCM), 2017:1-10. (CCF C 类)
Canping Su, Yan Yan, Si Chen, Hanzi Wang. An efficient deep neural networks training framework for robust face recognition. Proceeding of the IEEE Conference on Image Processing, 2017. (CCF C类)
Xiong Zhou, Hanzi Wang, Guobao Xiao, Xing Wang, Yan Yan, Liming Zhang. Weighted median-shift on graphs for geometric model fitting. Proceeding of the IEEE Conference on Image Processing, 2017. (CCF C 类)
Yuan Fang, Yan Yan, Si Chen, Hanzi Wang, and Chang Shu. Sparse similarity metric learning for kinship verification. Proceedings of the IEEE International Conference on Visual Communications and Image Processing (VCIP), 2016.
Xing Wang, Guobao Xiao, Yan Yan, and Hanzi Wang. Message passing on the two-layer network for geometric model fitting. Proceedings of the Asian Conference on Computer Vision (ACCV), 2016. (CCF C类)
Hanzi Wang, Guobao Xiao, Yan Yan, David Suter, Mode-seeking on Hypergraphs for robust geometric model fitting. International Conference on Computer Vision (ICCV), 2015. (CCF A类)
Zhenhai Liu, Hanzi Wang, Yan Yan, Guanjun Guo. Effective Facial Expression Recognition via the Boosted Convolutional Neural Network. Chinese Conference on Computer Vision (CCCV), 2015.
Riwei Chen, Yan Yan, Min Liu, and Hanzi Wang, Comparative study: face recognition via the correlation filter technique, International Conference on Internet Multimedia Computing and Service (ICIMCS), 2014.
Yuanyuan Shen, Yan Yan, and Hanzi Wang, Low rank metric learning via accelerated gradient optimization, International Conference on Internet Multimedia Computing and Service (ICIMCS),  2014.
Min Liu, Yan Yan, Riwei Chen, and Hanzi Wang, The state-of-the-art research progress on motion segmentation, International Conference on Internet Multimedia Computing and Service (ICIMCS),  2014.
Dong Yan, Yuanyuan Shen, Yan Yan, and Hanzi Wang, Non-linear feature fusion based on polynomial correlation filter for face recognition, International Conference on Intelligence Science and Big Data Engineering (IScIDE), 2013.
Dong Yan, Yan Yan, and Hanzi Wang, Robust head pose estimation with a new principal optimal tradeoff filter, International Conference on Intelligence Science and Big Data Engineering (IScIDE), 2013.
Zhihui Chen, Yan Yan, and Hanzi Wang, Visual saliency detection via homology distribution and color contrast, International Conference on Intelligence Science and Big Data Engineering (IScIDE), 2013.
Zizhao Zhang, Yan Yan, and Hanzi Wang, Discriminative filter based regression learning for facial expression recognition, Proceedings of IEEE Conference on Image Processing (ICIP), 2013. (CCF C类)
Yan Yan, Hanzi Wang, Cuihua Li, Chenhui Yang, and Bineng Zhong, A novel unconstrained correlation filter and its application in face recognition, Proceedings of Sino-foreign-interchange workshop on Intelligence Science and Intelligent Data Engineering (IScIDE), 2012.
Chaoxin Lv, Yan Yan, and Hanzi Wang, Robust visual tracking with the cross-bin metric, Proceedings of IEEE Conference on Pattern Recognition (ICPR), 2012. (CCF C类)
Guanglu Liu, Yan Yan, and Hanzi Wang, Accelerated robust sparse coding for fast face recognition, Proceedings of IEEE Conference on Pattern Recognition (ICPR), 2012. (CCF C类)
Yan Yan and Yujin Zhang, Effective Discriminant Feature Extraction for Face Recognition, Proceedings of International Symposium on Communications, Control and Signal Processing, 2010.
Bo Han, Yan Yan, Zhenghua Chen, Chang Liu and Weiguo Wu, A general framework for automatic on-line replay detection in sports video, Proceedings of ACM Multimedia (MM) 2009. (CCF A类)
Yan Yan and Yujin Zhang, Class-dependence Feature Analysis Face Recognition Method based on 1-D Correlation Filter, Proceedings of National Conference on Image and Graphics (NCIG), Fuzhou, China, 2008. (Best student paper award)
Yan Yan and Yujin Zhang, Multimodal Biometrics Fusion with Correlation Filter bank, IEEE Conference on Pattern Recognition (ICPR), 2008. (CCF C类)

发明专利: 

王菡子;刘光禄;严严;一种新的人脸特征描述方法。专利号:ZL 2013 1045 0629.1.
王菡子;肖国宝;严严;基于超图模式搜索的鲁棒拟合方法。专利号:ZL 2015 1 0269932.0.
王菡子;郭冠军;严严;基于卷积神经网络的快速目标检测方法。专利号:ZL 2015 1 0061852.6.
严严;晏栋;沈媛媛;王菡子;一种人脸姿态检测方法与在人脸识别中的应用。专利号:ZL 2013 1 0241306.1(2013-06-18)
严严;Chunhua Shen;王菡子;基于拉格朗日对偶的半正定谱聚类方法。专利号:ZL 2012 1 0445602.9(2012-11-08)
严严;陈日伟;王菡子;基于混合训练的深度学习人脸验证方法。专利号:ZL 2016 1 0592954.5 (2019年9月20日)
严严, 陈日伟, 王菡子. 基于多任务深度学习的人脸属性识别方法. 中国发明专利, 专利号: ZL 2016 1 0592958.6, 2020.
严严, 杜伊涵, 王菡子. 基于长短时记忆网络的目标跟踪方法. 中国发明专利, 专利号: ZL
2018 1 0323668.8, 2020.

Top